CN101622616A - Shared language model - Google Patents

Shared language model Download PDF

Info

Publication number
CN101622616A
CN101622616A CN200880006684A CN200880006684A CN101622616A CN 101622616 A CN101622616 A CN 101622616A CN 200880006684 A CN200880006684 A CN 200880006684A CN 200880006684 A CN200880006684 A CN 200880006684A CN 101622616 A CN101622616 A CN 101622616A
Authority
CN
China
Prior art keywords
input pattern
data
logograph
stroke
language model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN200880006684A
Other languages
Chinese (zh)
Other versions
CN101622616B (en
Inventor
D·李
Q·X·J·李
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Microsoft Technology Licensing LLC
Original Assignee
Microsoft Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Microsoft Corp filed Critical Microsoft Corp
Publication of CN101622616A publication Critical patent/CN101622616A/en
Application granted granted Critical
Publication of CN101622616B publication Critical patent/CN101622616B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/274—Converting codes to words; Guess-ahead of partial word inputs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/53—Processing of non-Latin text

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Document Processing Apparatus (AREA)

Abstract

A shared language model may be provided. First, a first input may be received. Then, in response to the first input, an input mode may be determined comprising one of the following: a pinyin input mode, a stroke order input mode, and a stroke number input mode. Then, data may be received based on the determined input mode. The received data may be converted using the determined input mode and using a language model. The language model may be configured to be used with each of the following input modes: the pinyin input mode, the stroke order input mode, and the stroke number input mode.

Description

Share language model
Background
Chinese character is the logograph that uses when hand-written Chinese.The Shang Dynasty of complete Chinese-character writing system before 3200 occurs in China period, thereby makes it be considered to the oldest " existing " writing system.Because the logograph that uses when writing Chinese mainly is a pictograph, thus the language archaeologist soluble with the getting in touch of modern Chinese writing system.Therefore, because use thousands of different logographs in the Chinese, so the keyboard that is difficult to use a computer is imported Chinese.
The expression Chinese character a kind of mode be to use " phonetic " (wherein the meaning of " assembly " be " spelling " and the meaning of " sound " is " sound ").Phonetic is a kind ofly to use Roman alphabet to represent Chinese character and express the mode of the sound in the Chinese.Have the other system be used to express mandarin Chinese, but phonetic is to be accepted most and by the most widely used.In case will knowing, association, the people who learned phonetic how to use Chinese dictionary to read any word in the mandarin.Phonetic also is that Chinese character is input to modal mode in the computing machine.Although phonetic and English all use Roman alphabet, many letters are not that the same sound of using is in English expressed.
In addition, expressed word uses the set of 21 kinds of sound to represent to be called as the beginning of the word of initial consonant in the phonetic, and uses the set of 37 kinds of sound to represent to be called as the ending of the word of simple or compound vowel of a Chinese syllable.These sound combinations are to form about 420 kinds of different sound.For example, the expressed word corresponding to " flower " is " hu ā " in the phonetic.In this word, letter " h " is an initial consonant and " u ā " is simple or compound vowel of a Chinese syllable.In addition, common combined characters is to form compound.For example, the expressed word corresponding to " China " is " zh ō nggu ó " in the phonetic.The meaning of Zh ō ng be in the middle of (initial consonant: " zh ", simple or compound vowel of a Chinese syllable: " ō ng ") and the meaning of gu ó be country's (initial consonant: " g ", simple or compound vowel of a Chinese syllable: " u ó ").
In addition, the word that has same pronunciation in the mandarin can be depending on and how to say this word and have different implications.How the tone of speaker's speech changed when " tone " of the word in the Chinese was described in this word.In mandarin, there be four kinds " tone ".These tones are represented by the mark above the word in phonetic.
Have on the conventional computing machine of qwerty keyboard, may only have the voice or the phonetic input process that are used for input in Chinese.Yet, adopting conventional phonetic input process, the user can't not know phonetic or not exist under the situation of the phonetic of distributing to specific Chinese character to import Chinese character at it.
General introduction
It is some notions that will further describe in the following detailed description for the form introduction of simplifying that this general introduction is provided.This general introduction is not intended to identify the key feature or the essential feature of theme required for protection.This general introduction is not intended to be used to limit the scope of theme required for protection yet.
Shared language model can be provided.At first, can receive first input.Then, in response to this first input, can determine to comprise one input pattern in the following input pattern: phonetic input pattern, stroke order input pattern and stroke number input mode.Can receive data based on determined input pattern then.Received data can be used determined input pattern and use language model conversion.This language model can be configured in following input pattern each use: phonetic input pattern, stroke order input pattern and stroke number input mode.
Aforementioned general description and following detailed description both provide example and just illustrative.Therefore, aforementioned general description and following detailed description should not be considered to restrictive.In addition, except also providing further feature or modification illustrated those herein.For example, each embodiment can relate to various characteristics combination and the sub-portfolio of describing in detailed description.
The accompanying drawing summary
Merge in the present invention and constitute its a part of accompanying drawing various embodiment of the present invention is shown.In the accompanying drawings:
Fig. 1 is the block diagram of an operating environment.
Fig. 2 is the process flow diagram that is used to provide the method for sharing language model;
Fig. 3 is the diagram that candidate window is shown; And
Fig. 4 is the block diagram that comprises the system of computing equipment.
Describe in detail
Below describe in detail with reference to each accompanying drawing.As possible, just use identical Reference numeral to indicate identical or similar element in the accompanying drawings and the description below.Although may describe various embodiments of the present invention, modification, reorganization and other realization also are possible.For example, can replace, add or revise the element shown in the accompanying drawing, and can be by disclosed method displacement, rearrangement or interpolation stage are revised method described herein.Therefore, below detailed description does not limit the present invention.On the contrary, correct scope of the present invention is defined by appended claims.
A kind of shared language model can be provided.Use has the conventional system of the desk-top or laptop computer of qwerty keyboard and only supports for example to be used for Chinese voice or phonetic input process.A problem of conventional phonetic input process is that the user may not know corresponding to the phonetic of required Chinese character or not exist under the situation of the phonetic of distributing to required Chinese character to import Chinese character at it.According to various embodiments of the present invention, can solve this phonetic input process problem based on the input process (for example, stroke order and stroke number input process) of stroke.For example, logograph (for example, Chinese character) can comprise radical parts and all the other strokes.Radical parts also comprises stroke.As will be described in more detail below, adopt the input process based on stroke, the user can import for example Chinese character under the situation of not knowing the character pronunciation.In addition, by using language model (LM), various embodiments of the present invention can provide higher transfer admittance to the user.
According to various embodiments of the present invention, Fig. 1 shows the exemplary operation environment that is used for integrated pinyin and stroke input system 100.The user imports 105 and can be input in the reading window 110 of user interface 115 by the user.The user imports 105 and can indicate the user to wish to call which edit model 120 and corresponding to the data of logograph (for example, Chinese character).For example, the user can provide input 105 to use phonetic input model 125, stroke order input model 130 or stroke number input model 135 with indicative of desired.Data corresponding to logograph can be sent to required edit model 120, this edit model 120 and then can use dictionary (for example, spelling book 140, stroke dictionary 145 or radical dictionary 150).Required edit model 120 can use corresponding to the data of logograph come with candidate window 155 that user interface 115 is associated in produce a plurality of logograph candidates.In addition, can use LM 160 to provide higher transfer admittance to the user.For example, LM 160 can be used for predicting logograph by frequency of utilization or based on previous logograph.LM 160 can share between phonetic input model 125, stroke order input model 130 and stroke number input model 135.A plurality of logograph candidates can improve and be placed in synthetic and the prediction window 165 by LM 160.
Fig. 2 sets forth to be used for providing the method 200 of the sharing language model process flow diagram in each related summary stage according to one embodiment of the invention.Method 200 can be used as realizing at the computing equipment of describing in more detail below with reference to Fig. 1 100.Below the mode in each stage of implementation method 200 will be described in more detail.Method 200 can start from initial block 205 and proceed to the stage 210, and computing equipment 100 can receive first input there.For example, the user can use keyboard that this first is input in the computing equipment 400.This input can comprise key sequence, and it is corresponding to for example phonetic input pattern, stroke order input pattern or stroke number input mode.In addition, this first input can receive with mouse option from menu in response to the user.Project in the menu can be corresponding to phonetic input pattern, stroke order input pattern and stroke number input mode.As mentioned above, various embodiments of the present invention can support simultaneously via the keyboard input process leading key, select or the input process of any other type via the menu item of mouse input process.In addition, this first input can comprise the data of wishing to be input to the logograph in the computing equipment 400 corresponding to the user.Though various embodiments of the present invention are described in the context of Chinese character, can use any based on based on the language of logograph and the invention is not restricted to Chinese.
Receive stage 210 of first input from computing equipment wherein 100, method 200 can advance to the stage 220, and computing equipment 100 can be determined input pattern in response to this first input there.For example, this input pattern can comprise phonetic input pattern, stroke order input pattern or stroke number input mode.For example, computing equipment can be resolved first input to determine whether this first input comprises the key sequence corresponding to the phonetic input pattern." Ctrl p " in this first input can indicate user expectation to call the phonetic input pattern.In addition, computing equipment can be resolved first input to determine whether this first input comprises the key sequence corresponding to the stroke order input pattern." Ctrl so " in this first input can indicate user expectation to call the stroke order input pattern.In addition, computing equipment can be resolved first input to determine whether this first input comprises the key sequence corresponding to stroke number input mode." Ctrl sn " in this first input can indicate user expectation to call stroke number input mode.
In case computing equipment 100 is determined input pattern in the stage 220, method 200 just can proceed to the stage 230, and computing equipment 100 can receive data based on determined input pattern there.For example, except aforesaid key sequence corresponding to user's required mode, first input can comprise the data of wishing to be input to the logograph in the computing equipment 400 corresponding to the user.Data type of being accepted and accepting method can be depending on as the above indicated pattern of user with reference to stage 210 descriptions.
Computing equipment 100 received data in the stage 230 after, method 200 can proceed to the stage 240, there the computing equipment 100 convertible data that receive.Computing equipment 100 can use determined input pattern and language model 160 to change the data that receive.For example, this language model can be configured to as will be in the following following input pattern of explaining in more detail each use: phonetic input pattern, stroke order input pattern and stroke number input mode.
About the phonetic input pattern, as mentioned above, phonetic is to can be used as the Chinese speech system that Roman character is imported.For example, " hua " is the phonetic corresponding to following at least Chinese character " flower ", " China " and " words ".For example, when the user was input in the equipment 400 with " hua ", equipment 400 can present a plurality of Chinese characters (for example, comprising above mentioned Chinese character) in candidate window 300 as shown in Figure 3.The user can select the required Chinese character in a plurality of Chinese characters then from candidate window 300.
For the stroke order input pattern, for example, each Chinese character all can be write by pen in order.Employed stroke can comprise five basic strokes in the Chinese, for example, and " one ", " Shu ", " Pie ", " Dian " He “ Ya ".These strokes can be distributed corresponding keyboard coding respectively, and for example 1,2,3,4 and 5.Therefore, under the situation of stroke order input, Chinese character " flower " can be produced by first input that comprises sequence " 1223235 ".
About stroke number input mode, each Chinese character all comprises radical parts and all the other strokes.Radical parts also can comprise stroke.According to various embodiments of the present invention, the stroke number input can be based on dictionary lookup.Chinese character can be at first based on radical, and searches in dictionary based on all the other strokes except that radical then.Therefore, Chinese character can be imported with stroke number input mode by dual mode is next at least: i) total stroke number input (can produce long candidate list); And ii) radical and stroke number input (can produce short candidate list).
Under the situation of total stroke number input, total stroke number of Chinese character can be counted by the user.Then, the user can be input to stroke number the tabulation that has the Chinese character of this stroke number in the equipment 400 with generation.For example, " flower " has total stroke number 7.As a result, the user can be input in the equipment 400 7.Therefore, equipment 400 can show the candidate window of the Chinese character that has 7 separately.
Under the situation of radical and stroke number input, user's count enable and input corresponding to the stroke number of radical parts so that from the radical candidate list, find out correct radical.Then, user's count enable and import all the other stroke numbers and from candidate list, select correct Chinese character.For example, under the situation of " flower ", radical is " Lv ".In addition, all the other strokes are " Pie ", " Shu ", “ Ya " and " Pie " (for example, " Pie "+" Shu "=＞" Ren " and " Pie "+“ Ya "=＞" an ancient type of spoon ").The stroke number of " Lv " can be 3 and all the other strokes can be 4.Therefore, the user can be input in the equipment 400 so that find out radical " Lv " from the radical candidate list 3.This user can continue to import all the other stroke numbers 4 then and make as a whole correct Chinese character to find out.
As mentioned above, except using determined input pattern, computing equipment 100 can use language model 160 to change the data that receive.In all input patterns (for example, phonetic input pattern, stroke order input pattern and stroke number input mode), can use identical language model (for example, LM 160).In other words, according to various embodiments of the present invention, all input patterns can be shared same language model.In addition, LM 160 can use by following dual mode at least, presses: i) intelligent conversion mode; And by ii) input prediction.
About intelligent conversion, LM 160 can comprise the language statistics knowledge system that uses based on extensive language.Given user's input, LM 160 can help to consider that for example the frequency of utilization and the input context of word provide most possible conversion.For example, as shown in Figure 3, equipment 400 can provide first input to produce candidate 1 to 9 in response to the user.In addition, by using LM 160, equipment 400 can come these candidates are sorted by the frequency of utilization of candidate 1 to 9 in given language (for example, Chinese) in window 300.In other words, for candidate 1 to 9, candidate 1 may be the character of the most frequent use and candidate 9 may be least frequent the use.Candidate 2-8 can fall into the frequency of utilization between candidate 1 and 9 respectively.
For the input prediction, based on the content (for example, previous character) that the user has imported, the input prediction can help to provide most possible Chinese character or the word that the user then may import.This prediction can be based on existing dictionary (for example, spelling book 140, stroke dictionary 145 and radical dictionary 150) and also based on nearest input history/content.For example, the user may import " north ".Therefore, by using LM 160, " capital " can be predicted to be next most possible character, because " Beijing " is the frequent word that uses in the language of correspondence with the input prediction.In other words, can produce " capital " as candidate (and for example other candidates).Therefore, " capital " can (for example be given the highest rank in candidate window, with respect to other candidates in this candidate window) because equipment 400 can be by using LM 160 to determine that " capital " is the most possible character that the user may import afterwards in " north " with the input prediction.In addition, various embodiments of the present invention can provide " capital " not to be placed in the candidate window with " capital " to user's demonstration " Beijing " and to allow the user select " capital " from this candidate window in " north " afterwards.According to various embodiments of the present invention, no matter " north " still is that all measurable " capital " is because all patterns can be shared LM 160 with the input of stroke input pattern with spelling mode.In case the data that computing equipment 100 is received in stages 240 transfer changing-over, method 200 just can finish at stages 250 place then.
Can comprise the system that is used to provide conversion according to one embodiment of the invention.This system can comprise memory stores and be coupled to the processing unit of this memory stores.This processing unit can be used for receiving first input and determines to comprise one input pattern in the following input pattern in response to this first input: phonetic input pattern, stroke order input pattern and stroke number input mode.This processing unit can be used for receiving data based on determined input pattern.In addition, this processing unit can be used for using determined input pattern and use to be configured to the data that each the language model conversion of using in following input pattern receives: phonetic input pattern, stroke order input pattern and stroke number input mode.
Can comprise the system that is used to provide conversion according to another embodiment of the present invention.This system can comprise memory stores and be coupled to the processing unit of this memory stores.This processing unit can be used for determining to comprise one input pattern in the following input pattern: stroke order input pattern and stroke number input mode.In addition, this processing unit can be used for receiving data based on determined input pattern.In addition, this processing unit can be used for based on determined input pattern and is configured to the data that each the language model conversion of using in following input pattern receives: phonetic input pattern, stroke order input pattern and stroke number input mode.
Can comprise the system that is used to provide conversion according to still another embodiment of the invention.This system can comprise memory stores and be coupled to the processing unit of this memory stores.This processing unit can be used for receiving to the selection from first translative mode of following input pattern: phonetic input pattern, stroke order input pattern and stroke number input mode.This processing unit also can be used for changing first data based on first translative mode and language model.In addition, this processing unit can be used for receiving to being different from this first translative mode and being selected from the selection of second translative mode of following input pattern: phonetic input pattern, stroke order input pattern and stroke number input mode.In addition, this processing unit can be used for changing second data based on second translative mode and language model.
Fig. 4 is the block diagram that comprises the system of computing equipment 400.According to one embodiment of the invention, above-mentioned memory stores and processing unit can be realized in the computing equipments such as computing equipment 400 such as Fig. 4.Can use the combination of any suitable hardware, software or firmware to realize this memory stores and processing unit.For example, memory stores and processing unit can be realized with computing equipment 400 or in conjunction with any other computing equipment 418 of computing equipment 400.According to various embodiments of the present invention, said system, equipment and processor are examples, and other system, equipment and processor can comprise above-mentioned memory stores and processing unit.In addition, computing equipment 400 can comprise the operating environment that is used for as the above system of describing with reference to figure 1 100.Computing equipment 400 can be operated and be not limited in system 100 in other environment.
With reference to figure 4, can comprise such as computing equipment 400 computing equipments such as grade according to the system of one embodiment of the invention.In basic configuration, computing equipment 400 can comprise at least one processing unit 402 and system storage 404.The configuration and the type that depend on computing equipment, system storage 404 can include, but not limited to volatile memory (for example, random-access memory (ram)), nonvolatile memory (for example, ROM (read-only memory) (ROM)), flash memory or any combination.System storage 404 can comprise operating system 405, one or more programming module 406, and can comprise spelling book 140, stroke dictionary 145, radical dictionary 150, language model 160 and routine data 407.For example, operating system 405 is applicable to the operation of control computing equipment 400.In one embodiment, programming module 406 for example can comprise, conversion application 420.In addition, various embodiments of the present invention can be put into practice in conjunction with shape library, other operating system or any other application program, and are not limited to any application-specific or system.This basic configuration is illustrated by the assembly in the dotted line 408 in Fig. 4.
Computing equipment 400 also can have supplementary features or function.For example, computing equipment 400 also can comprise additional data storage device (removable and/or not removable), such as, for example disk, CD or tape.These extra storage in Fig. 4 by removable storage 409 with can not mobile storage 410 illustrate.Computer-readable storage medium can comprise the volatibility that realizes with any method or the technology that is used to store such as information such as computer-readable instruction, data structure, program module or other data and non-volatile, removable and removable medium not.System storage 404, removable storage 409 and can not mobile storage 410 all be the example (that is memory stores) of computer-readable storage medium.Computer-readable storage medium can comprise, but be not limited to RAM, ROM, electricallyerasable ROM (EEROM) (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, tape cassete, tape, disk storage or other magnetic storage apparatus or can be used for canned data and can be by any other medium of computing equipment 400 visit.Any such computer-readable storage medium can be the part of equipment 400.Computing equipment 400 can also have input equipment 412, as keyboard, mouse, pen, audio input device, touch input device etc.Also can comprise such as output devices 414 such as display, loudspeaker, printers.The said equipment is example and can uses miscellaneous equipment.
Computing equipment 400 also can comprise and can allow equipment 400 to communicate to connect 416 such as coming by the network in for example Intranet or the Internet distributed computing environment with other computing equipments 418 communicate.Communicating to connect 416 is examples of communication media.Communication media is usually by embodying such as computer-readable instruction, data structure, program module or other data in the modulated message signal such as carrier wave or other transmission mechanism, and comprises any information transmitting medium.Term " modulated message signal " refers to be provided with or change in the mode that the information in the signal is encoded the signal of its one or more features.As example and unrestricted, communication media comprises such as cable network or direct wire medium such as line connection, and such as wireless mediums such as acoustics, radio frequency (RF), infrared ray and other wireless mediums.Term computer-readable medium can comprise storage medium and communication media as used herein.
As mentioned above, can in system storage 404, store a plurality of program modules and the data file that comprises operating system 405.When carrying out on processing unit 402, programming module 406 (for example, conversion application 420) can be carried out each process, for example comprises the stage of aforesaid one or more methods 200.Aforementioned process is an example, and processing unit 402 can be carried out other process.Can comprise Email and contact application, word-processing application, spreadsheet applications, database application, slide presentation applications, drawing or computer-assisted application program etc. according to operable other programming module of various embodiments of the present invention.
Generally speaking, according to various embodiments of the present invention, program module can comprise can carry out the structure that particular task maybe can realize routine, program, assembly, data structure and other type of specific abstract data type.In addition, various embodiments of the present invention can be put into practice with other computer system configurations, comprise portable equipment, multicomputer system, based on the system of microprocessor or programmable consumer electronics, minicomputer, mainframe computer etc.Various embodiments of the present invention also realize in the distributed computing environment of task by the teleprocessing equipment execution that links by communication network therein.In distributed computing environment, program module can be arranged in local and remote memory storage device.
In addition, various embodiments of the present invention can comprise the circuit of discrete electronic component, comprise logic gate encapsulation or integrated electronic chip, utilize microprocessor circuit or comprising on the single chip of electronic component or microprocessor and realize.Various embodiments of the present invention can also use can carry out such as, for example, AND (with), OR (or) and other technology of NOT logical operations such as (non-) put into practice, include but not limited to machinery, optics, fluid and quantum technology.In addition, various embodiments of the present invention can realize in multi-purpose computer or any other circuit or system.
For example, various embodiments of the present invention can be implemented as computer procedures (method), computing system or such as goods such as computer program or computer-readable mediums.Computer program can be the computer-readable storage medium of computer program that computer system-readable and coding are used for the instruction of object computer process.Computer program also can be the transmitting signal on the carrier wave of computer program of the readable and coding of the computing system instruction that is used for the object computer process.Therefore, the present invention can specialize with hardware and/or software (comprising firmware, resident software, microcode etc.).In other words, various embodiments of the present invention can adopt include on it for instruction execution system use or in conjunction with the computing machine of its use can use the computing machine of computer readable program code can use or computer-readable recording medium on the form of computer program.Computing machine can use or computer-readable medium can be can comprise, store, communicate by letter, propagate or transmission procedure for instruction execution system, device or equipment uses or in conjunction with any medium of its use.
Computing machine can use or computer-readable medium can be, for example, but is not limited to electricity, magnetic, light, electromagnetism, infrared or semiconductor system, device, equipment or propagation medium.Computer-readable medium examples (non-exhaustive list) more specifically, computer-readable medium can comprise following: electrical connection, portable computer diskette, random-access memory (ram), ROM (read-only memory) (ROM), Erasable Programmable Read Only Memory EPROM (EPROM or flash memory), optical fiber and portable compact disk ROM (read-only memory) (CD-ROM) with one or more lead.Note, computing machine can use or computer-readable medium even can be to print paper or another the suitable medium that program is arranged on it, because program can be via for example to the optical scanning of paper or other medium and catch electronically, subsequently if necessary by compiling, explanation, or with other suitable manner processing, and be stored in the computer memory subsequently.
For example, reference has been described various embodiments of the present invention according to the block diagram and/or the operational illustration yet of method, system and the computer program of various embodiments of the present invention more than.Each function/action of being indicated in the frame can occur by being different from the order shown in any process flow diagram.For example, depend on related function/action, in fact two frames that illustrate continuously can be carried out basically simultaneously, and perhaps these frames can be carried out by opposite order sometimes.
Although described some embodiment of the present invention, also may have other embodiment.In addition, though various embodiments of the present invention be described to be stored in storer and other storage medium in data be associated, but data can also be stored in or read the computer-readable medium from other type, as secondary memory device, as hard disk, floppy disk or CD-ROM, from the carrier wave of the Internet or the RAM or the ROM of other form.In addition, each stage of disclosed each method can revise by any means, comprises by to each stage rearrangement and/or insertion or deletion stage, and does not deviate from the present invention.
The all authority that comprises the copyright in the included code herein all belongs to the applicant and is this application people's property.The applicant keeps and keeps all authority in the included code herein, and only authorizes about the reproduction of the patent of being authorized and the permission of not reproducing this material for other purpose.
Though this instructions comprises each example, scope of the present invention is indicated by appended claims.In addition, although used to the language description of architectural feature and/or the special use of method logical action this instructions, claims are not limited to above-mentioned feature or action.On the contrary, above-mentioned concrete feature and action are to come disclosed as the example of various embodiments of the present invention.

Claims (20)

1. method that is used to provide conversion, described method comprises:
Receive first input (210);
Import one the input pattern of determining to comprise in the following input pattern in response to described first: phonetic input pattern, stroke order input pattern and stroke number input mode;
Receive data (230) based on determined input pattern; And
Change received data (240), comprising:
Use determined input pattern, and
Use is configured to each language model that uses in following input pattern: described phonetic input pattern (125), described stroke order input pattern (130) and described stroke number input mode (135).
2. the method for claim 1 is characterized in that, receives described first input (210) and comprises that reception comprises first input of Client-initiated keyboard sequence (105).
3. the method for claim 1, it is characterized in that, receive described data (230) based on determined input pattern and be included in determined input pattern and receive the data that comprise corresponding to a plurality of Roman characters of Chinese pinyin when comprising described phonetic input pattern (125).
4. the method for claim 1, it is characterized in that, receive described data (230) based on determined input pattern and be included in determined input pattern and receive the data that comprise a plurality of arabic numeral when comprising described stroke order input pattern (130), each in described a plurality of arabic numeral all corresponding to a plurality of basic strokes that writing system based on logograph is associated in one.
5. the method for claim 1, it is characterized in that, receive described data (230) based on determined input pattern and be included in determined input pattern and receive the data that comprise a plurality of arabic numeral when comprising described stroke order input pattern (130), each in described a plurality of arabic numeral is all corresponding to one in a plurality of basic Chinese stroke that comprises following stroke: " one ", " Shu ", " Pie ", " Dian " He “ Ya ".
6. the method for claim 1, it is characterized in that, receive described data (230) based on determined input pattern and be included in determined input pattern and receive the data that comprise corresponding to the integer of the stroke number in the logograph when comprising described stroke number input mode (135).
7. the method for claim 1, it is characterized in that, receive described data (230) based on determined input pattern and be included in determined input pattern and receive the data that comprise corresponding to the integer of the stroke number in the logograph that comprises Chinese character when comprising described stroke number input mode (135).
8. the method for claim 1, it is characterized in that, receive described data (230) based on determined input pattern and be included in determined input pattern and receive when comprising described stroke number input mode (135) and comprise corresponding to first integer of the radical that is associated with logographic characters with corresponding to the data of second integer of the stroke number except that the described radical of Chu in the described logograph.
9. the method for claim 1, it is characterized in that, receiving described data (230) based on determined input pattern is included in determined input pattern and receives when comprising described stroke number input mode (135) and comprise that described logograph comprises Chinese character corresponding to first integer of the radical that is associated with logographic characters with corresponding to the data of second integer of the stroke number except described radical in the described logograph.
10. the method for claim 1 is characterized in that, when determined input pattern comprises described phonetic input pattern (125), changes received data (240) and comprising:
Demonstration is corresponding to a plurality of logographs (300) of Chinese pinyin, wherein use described language model (160) to comprise to use described language model (160) come by from language the least frequent order that uses in the described language of frequent use arrange described a plurality of logograph; And
Reception is to one selection in described a plurality of logographs.
11. the method for claim 1 is characterized in that, also is included in the described data of reception and receives previous logograph before, wherein, when determined input pattern comprises described phonetic input pattern (125), changes received data and comprises:
Demonstration is corresponding to a plurality of logographs (300) of Chinese pinyin, wherein uses described language model (160) to comprise to use described language model (160) to come to arrange described a plurality of logograph by the most frequent order that least frequently is used to follow described previous logograph to described language that is used for following described previous logograph from language; And
Reception is to one selection in described a plurality of logographs.
12. the method for claim 1 is characterized in that, when determined input pattern comprises described stroke number input mode (135), changes received data (240) and comprising:
Show a plurality of logographs have the stroke number that equals the integer that in described data, receives separately, wherein use described language model (160) to comprise to use described language model (160) come by from language the least frequent order that uses in the described language of frequent use arrange described a plurality of logograph; And
Reception is to one selection in described a plurality of logographs.
13. the method for claim 1 is characterized in that, also is included in the described data of reception and receives previous logograph before, wherein, when determined input pattern comprises described stroke number input mode (135), changes received data (240) and comprising:
Show a plurality of logographs have the stroke number that equals the integer that in described data, receives separately, wherein use described language model (160) to comprise to use described language model (160) to come to arrange described a plurality of logograph by the most frequent order that least frequently is used to follow described previous logograph to described language that is used for following described previous logograph from language; And
Reception is to one selection in described a plurality of logographs.
14. the method for claim 1 is characterized in that, when determined input pattern comprises described stroke number input mode (135), changes received data (240) and comprising:
Show a plurality of logographs, each logograph has the stroke number except described radical corresponding to the radical of first integer that receives and second integer that equals to receive in described data in described data, wherein use described language model (160) to comprise to use described language model (160) come by from language the least frequent order that uses in the described language of frequent use arrange described a plurality of logograph; And
Reception is to one selection in described a plurality of logographs.
15. the method for claim 1 is characterized in that, when determined input pattern comprises described stroke number input mode (135), changes received data (240) and comprising:
Show a plurality of logographs, each logograph has the stroke number except described radical corresponding to the radical of first integer that receives and second integer that equals to receive in described data in described data, wherein use described language model (160) to comprise to use described language model (160) to come to arrange described a plurality of logograph by the most frequent order that least frequently is used to follow described previous logograph to described language that is used for following described previous logograph from language; And
Reception is to one selection in described a plurality of logographs.
16. a system that is used to provide conversion, described system comprises:
Memory stores (404,409,410); And
Be coupled to the processing unit (402) of described memory stores (404,409,410), wherein said processing unit can be used for:
Determine to comprise one input pattern (220) in the following input pattern: stroke order input pattern (130) and stroke number input mode (135)
Receive data (230) based on determined input pattern; And
Change received data (240) based on determined input pattern and each language model that uses (160) of being configured in following input pattern; Phonetic input pattern (125), described stroke order input pattern (130) and described stroke number input mode (135).
17. system as claimed in claim 16, it is characterized in that, can be used for comprising the processing unit that can be used for based on create Chinese character by the order of a plurality of arabic numeral in the stroke of a plurality of arabic numeral indications in the received data and the received data, all comprise the Chinese stroke that is selected from following stroke by in the stroke of received a plurality of arabic numeral indications each: " one ", " Shu ", " Pie ", " Dian " He “ Ya " based on the processing unit (402) that determined input pattern is changed received data (240).
18. system as claimed in claim 16 is characterized in that, the processing unit (402) that can be used for changing based on determined input pattern received data (240) comprises the processing unit (402) that can be used for carrying out following action:
Show a plurality of logographs (300) have the stroke number that equals the integer that in described data, receives separately, wherein use described language model to comprise to use described language model come by from language the least frequent order that uses in the described language of frequent use arrange described a plurality of logograph; And
Reception is to one selection in described a plurality of logographs.
19. system as claimed in claim 16 is characterized in that, the processing unit (402) that can be used for changing based on determined input pattern received data (240) comprises the processing unit that can be used for carrying out following action:
Show a plurality of logographs, each logograph has the stroke number except described radical corresponding to the radical of first integer that receives and second integer that equals to receive in described data in described data, wherein use described language model to comprise to use described language model to come to arrange described a plurality of logograph by the most frequent order that least frequently is used to follow described previous logograph to described language that is used for following previous logograph from language; And
Reception is to one selection in described a plurality of logographs.
20. the computer-readable medium of one group of instruction of a storage, a kind of method that is used to provide conversion is carried out in described one group of instruction when being performed, and the method for being carried out by described one group of instruction comprises:
Reception is to the selection from first translative mode of following input pattern: phonetic input pattern (125), stroke order input pattern (130) and stroke number input mode (135);
Change first data (240) based on described first translative mode and language model;
Reception is to being different from described first translative mode and being selected from the selection of second translative mode of following input pattern: phonetic input pattern, stroke order input pattern and stroke number input mode; And
Change second data (240) based on described second translative mode and described language model.
CN2008800066849A 2007-03-01 2008-02-26 Shared language model Active CN101622616B (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US11/713,255 US8316295B2 (en) 2007-03-01 2007-03-01 Shared language model
US11/713,255 2007-03-01
PCT/US2008/055045 WO2008106470A1 (en) 2007-03-01 2008-02-26 Shared language model

Publications (2)

Publication Number Publication Date
CN101622616A true CN101622616A (en) 2010-01-06
CN101622616B CN101622616B (en) 2013-07-31

Family

ID=39721595

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2008800066849A Active CN101622616B (en) 2007-03-01 2008-02-26 Shared language model

Country Status (5)

Country Link
US (1) US8316295B2 (en)
JP (2) JP5513898B2 (en)
CN (1) CN101622616B (en)
TW (1) TWI428768B (en)
WO (1) WO2008106470A1 (en)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8677237B2 (en) 2007-03-01 2014-03-18 Microsoft Corporation Integrated pinyin and stroke input
KR101387510B1 (en) * 2007-10-02 2014-04-21 엘지전자 주식회사 Mobile terminal and method for controlling the same
US9330180B2 (en) * 2007-10-02 2016-05-03 Microsoft Technology Licensing, Llc Mobile terminal and method of controlling the same
US9733724B2 (en) * 2008-01-13 2017-08-15 Aberra Molla Phonetic keyboards
CN101719023A (en) * 2009-03-29 2010-06-02 李春华 Hand-held chinese character input keyboard and operation method
TWI412955B (en) * 2009-08-19 2013-10-21 Inventec Appliances Corp Method of prompting stroke order for chinese character, electronic device, and computer program product thereof
US20120023549A1 (en) * 2010-07-23 2012-01-26 Academia Sinica CAPTCHA AND reCAPTCHA WITH SINOGRAPHS
CN101930474A (en) * 2010-09-14 2010-12-29 闫卫 Chinese character simple stroke search method
US20120156658A1 (en) * 2010-12-16 2012-06-21 Nicholas Fuzzell Methods for teaching and/or learning chinese, and related systems
US8996356B1 (en) * 2012-04-10 2015-03-31 Google Inc. Techniques for predictive input method editors
CN104704510B (en) 2012-10-10 2018-08-31 摩托罗拉解决方案公司 Identify the method and apparatus that the language used in a document and the language based on identification execute OCR identifications
KR101337872B1 (en) * 2013-04-04 2013-12-06 주식회사 디오텍 Device and method for editing ink text data
US9460344B2 (en) * 2014-10-13 2016-10-04 Lenovo (Singapore) Pte. Ltd. Generating multi-logogram phrases from logogram radicals
US9910852B2 (en) * 2015-03-12 2018-03-06 Lenovo (Singapore) Pte. Ltd. Detecting cascading sub-logograms
US9886433B2 (en) * 2015-10-13 2018-02-06 Lenovo (Singapore) Pte. Ltd. Detecting logograms using multiple inputs

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1060544A (en) * 1991-09-28 1992-04-22 肖启宏 Computer input system for chinese-character holographic codes
US5197810A (en) * 1989-06-19 1993-03-30 Daozheng Zhang Method and system for inputting simplified form and/or original complex form of Chinese character
CN1412654A (en) * 2001-10-19 2003-04-23 陈永康 Association characters screening mode
US6809725B1 (en) * 2000-05-25 2004-10-26 Jishan Zhang On screen chinese keyboard

Family Cites Families (39)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS56132664A (en) * 1980-03-19 1981-10-17 Sharp Corp Electronic dictionary for kanji (japanese character)
JPH0743709B2 (en) * 1986-01-13 1995-05-15 カム―フー・ウォン Kanji input processing device
GB8629908D0 (en) * 1986-12-15 1987-01-28 Kemano Ltd Words & characters computer input device
JPH0320857A (en) * 1989-06-19 1991-01-29 Canon Inc Document processor
JPH05282294A (en) 1992-03-30 1993-10-29 Gakken Co Ltd Retrieving method for kanji @(3754/24)chinese character)
JPH07114558A (en) * 1993-10-19 1995-05-02 Fujitsu Ltd Chinese character conversion correcting process system
JPH0896081A (en) 1994-09-29 1996-04-12 Toshiba Corp Character recognizing device and character recognizing method
JP3233803B2 (en) 1994-12-22 2001-12-04 三菱重工業株式会社 Hard-to-read kanji search device
US5893133A (en) * 1995-08-16 1999-04-06 International Business Machines Corporation Keyboard for a system and method for processing Chinese language text
US5966719A (en) * 1997-11-20 1999-10-12 Microsoft Corporation Method for inserting capitalized Latin characters in a non-Latin document
US7257528B1 (en) * 1998-02-13 2007-08-14 Zi Corporation Of Canada, Inc. Method and apparatus for Chinese character text input
FI112978B (en) * 1999-09-17 2004-02-13 Nokia Corp Entering Symbols
JP2001166868A (en) * 1999-12-08 2001-06-22 Matsushita Electric Ind Co Ltd Method and device for inputting chinese pin-yin by numeric key pad
WO2001090879A1 (en) * 2000-05-26 2001-11-29 Telefonaktiebolaget Lm Ericsson (Publ) Method and apparatus for displaying information
JP4491921B2 (en) * 2000-06-16 2010-06-30 ブラザー工業株式会社 Japanese input device
US7254269B2 (en) * 2000-08-31 2007-08-07 Hewlett-Packard Development Company, L.P. Character recognition system
JP2005508031A (en) * 2001-08-30 2005-03-24 アメリカ オンライン インコーポレーティッド Adaptable stroke order system based on radicals
JP4252955B2 (en) * 2002-07-01 2009-04-08 ソニー エリクソン モバイル コミュニケーションズ， エービー Method for entering text into an electronic communication device
CN1515985A (en) * 2003-01-08 2004-07-28 时空系统有限公司 Digital information processing device and Chinese character input method
EP1586191A4 (en) * 2003-01-22 2009-03-11 Min-Kyum Kim Apparatus and method for inputting alphabet characters
CA2638965A1 (en) * 2003-05-15 2004-11-15 Ibm Canada Limited - Ibm Canada Limitee Accessing a platform independent input method editor from an underlying operating system
US20050027534A1 (en) * 2003-07-30 2005-02-03 Meurs Pim Van Phonetic and stroke input methods of Chinese characters and phrases
JP2005078211A (en) * 2003-08-28 2005-03-24 Fujitsu Ltd Chinese input program
JP2005157472A (en) * 2003-11-20 2005-06-16 Sharp Corp Character input device and method
JP4133851B2 (en) * 2004-01-28 2008-08-13 シャープ株式会社 Electronic dictionary device and electronic dictionary control program
US7478033B2 (en) * 2004-03-16 2009-01-13 Google Inc. Systems and methods for translating Chinese pinyin to Chinese characters
KR20050092999A (en) * 2004-03-17 2005-09-23 샤프전자(주) Chinese character searching method at electronic dictionary
CN1704882A (en) * 2004-05-26 2005-12-07 微软公司 Asian language input by using keyboard
US20060018545A1 (en) * 2004-07-23 2006-01-26 Lu Zhang User interface and database structure for Chinese phrasal stroke and phonetic text input
TWI249688B (en) * 2004-09-29 2006-02-21 Inventec Corp Human-machine interactive interface language conversion method and system
US7263658B2 (en) * 2004-10-29 2007-08-28 Charisma Communications, Inc. Multilingual input method editor for ten-key keyboards
KR100641838B1 (en) * 2004-11-10 2007-02-28 이병환 Method and system for inputing multi-language using symbol mixing text
US7889927B2 (en) * 2005-03-14 2011-02-15 Roger Dunn Chinese character search method and apparatus thereof
CN1834865B (en) * 2005-03-18 2010-04-28 马贤亮 Multi-character continuous inputting method of Chinese phonetic and notional phonetic alphabet with digitally coded on keypad
US7506254B2 (en) * 2005-04-21 2009-03-17 Google Inc. Predictive conversion of user input
US8032357B2 (en) * 2005-06-14 2011-10-04 Microsoft Corporation Phonetic input using a keypad
US7861164B2 (en) * 2005-11-03 2010-12-28 Bin Qin Method to sequentially encode PINYIN of Chinese character with few symbols
US8677237B2 (en) 2007-03-01 2014-03-18 Microsoft Corporation Integrated pinyin and stroke input
US20080211777A1 (en) 2007-03-01 2008-09-04 Microsoft Corporation Stroke number input

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5197810A (en) * 1989-06-19 1993-03-30 Daozheng Zhang Method and system for inputting simplified form and/or original complex form of Chinese character
CN1060544A (en) * 1991-09-28 1992-04-22 肖启宏 Computer input system for chinese-character holographic codes
US6809725B1 (en) * 2000-05-25 2004-10-26 Jishan Zhang On screen chinese keyboard
CN1412654A (en) * 2001-10-19 2003-04-23 陈永康 Association characters screening mode

Also Published As

Publication number Publication date
US8316295B2 (en) 2012-11-20
JP2014139809A (en) 2014-07-31
JP5802292B2 (en) 2015-10-28
CN101622616B (en) 2013-07-31
TWI428768B (en) 2014-03-01
TW200849038A (en) 2008-12-16
WO2008106470A1 (en) 2008-09-04
JP2010520530A (en) 2010-06-10
JP5513898B2 (en) 2014-06-04
US20080215307A1 (en) 2008-09-04

Similar Documents

Publication Publication Date Title
CN101622616B (en) Shared language model
CN101641691A (en) Integrated pinyin and stroke input
CN105117376B (en) Multi-mode input method editor
CN100555203C (en) Revise the system and method for input characters
US9824085B2 (en) Personal language model for input method editor
CN104813275B (en) For predicting the method and system of text
CN101669116A (en) Recognition architecture for generating asian characters
CN101622617A (en) Stroke number input
CN103026318A (en) Input method editor
CN101246410A (en) Contextual input method
CN101149679A (en) Method for adding self-defined word in input method word library and word input device
CN1704882A (en) Asian language input by using keyboard
van Esch et al. Writing across the world's languages: Deep internationalization for Gboard, the Google keyboard
WO2022108671A1 (en) Automatic document sketching
US7197184B2 (en) ZhuYin symbol and tone mark input method, and electronic device
TW201512858A (en) Electronic device and text-input interface displaying method thereof
CN102402298A (en) Pinyin input method and user word adding method and system of same
CN109284012A (en) A kind of Gu Yi nationality's text language in-put control system and method, information data processing terminal
CN115586839A (en) Method, system, and non-transitory computer-readable recording medium for inputting global text
WO2007132287A2 (en) Text composition
CN102346743A (en) Method and device for generating candidate words

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
ASS Succession or assignment of patent right

Owner name: MICROSOFT TECHNOLOGY LICENSING LLC

Free format text: FORMER OWNER: MICROSOFT CORP.

Effective date: 20150512

C41 Transfer of patent application or patent right or utility model
TR01 Transfer of patent right

Effective date of registration: 20150512

Address after: Washington State

Patentee after: Micro soft technique license Co., Ltd

Address before: Washington State

Patentee before: Microsoft Corp.